Cognitive education advisor

1. A computer implemented method for providing cognitive education advisory services, comprising: obtaining, by one or more processor of a cognitive education advisor, real time data including individual data from an individual device on person of a student attending a class, by an individual data collection agent running on the individual device, wherein the individual data collection agent communicates with the cognitive education advisor in real time, and wherein the individual device corresponding to the student is registered for the student in a student record for the student; identifying one or more activity of the student during the class from the real time data, based on a configuration for the cognitive education advisor specifying the one or more activities; correlating each of the one or more activity from the identifying with respective impact to performance of the student based on a performance record of the student record for the student, based on the configuration; calculating respective activity impact scores corresponding to the respective impacts, by use of predictive modeling on attributes of each of the one or more activity to the performance of the student; predicting the performance of the student in the class based on a collective activity impact score of the student in the class by adding up the respective activity impact scores from the calculating; generating one or more recommendation in order to improve the performance of the student, responsive to determining that predicted performance from the predicting is below a preconfigured threshold for the class; and communicating the one or more recommendation to a group of recipients specified for the student, wherein the method comprises analyzing geolocation data of the individual data in order to classify a seating position of the student in a classroom, wherein the seating position may be instantiated with a value selected from the group consisting of Front and Back, indicating respective areas within the classroom; and determining the seating position having a Front value as a positive activity and determining the seating position having a Back value as a negative activity, wherein the method comprises comparing the seating position of the student in comparison with a second seating position of a second student in proximity of the student and discovering that an activity impact score for a peer influence attribute of the second student is less than zero (0), wherein a value of the peer influence attribute is selected from the group consisting of one, zero, negative one (1, 0, −1), wherein one (1) indicates that the second student is helpful to nearby students and attentive, zero (0) indicates that the second student is neutral, and negative one (−1) indicates that the second student is disruptive to the class.

2. The computer implemented method of claim 1 , the generating comprising: rendering a recommendation not to take a seat near the second student, responsive to determining that the predicted performance is below the preconfigured threshold for the class, wherein the one or more recommendation from the generating includes the recommendation.

3. The computer implemented method of claim 1 , the generating comprising: rendering a recommendation not to take a seat near the second student.

4. The computer implemented method of claim 1 , further comprising: analyzing audio data of the real time data for content in order to classify a speech represented by the audio data into respective topics.

5. The computer implemented method of claim 1 , further comprising: analyzing audio data of the real time data for content in order to classify a speech represented by the audio data into respective topics; and determining the speech having a topic relevant to a subject of the class as a positive activity and determining the speech having a topic irrelevant to the subject as a negative activity.

6. The computer implemented method of claim 1 , further comprising: analyzing the real time data including audio data and movement data of the student in order to determine whether or not the student participates in the class, wherein participatory activities include raising a hand and asking questions; and discovering that the student does not participate in the class from the analyzing.

7. The computer implemented method of claim 6 , the generating comprising: rendering a recommendation to participate in the class by performing one or more of the participatory activities, responsive to determining that the predicted performance is below the preconfigured threshold for the class, wherein the one or more recommendation from the generating includes the recommendation.

8. A computer program product comprising: a computer readable storage medium readable by one or more processor and storing instructions for execution by the one or more processor for performing a method for providing cognitive education advisory services, comprising: obtaining real time data including individual data from an individual device on person of a student attending a class, by an individual data collection agent running on the individual device, wherein the individual data collection agent communicates with a cognitive education advisor in real time, and wherein the individual device corresponding to the student is registered for the student in a student record for the student; identifying one or more activity of the student during the class from the real time data, based on a configuration for the cognitive education advisor specifying the one or more activities; correlating each of the one or more activity from the identifying with respective impact to performance of the student based on a performance record of the student record for the student, based on the configuration; calculating respective activity impact scores corresponding to the respective impacts, by use of predictive modeling on attributes of each of the one or more activity to the performance of the student; predicting the performance of the student in the class based on a collective activity impact score of the student in the class by adding up the respective activity impact scores from the calculating; generating one or more recommendation in order to improve the performance of the student, responsive to determining that predicted performance from the predicting is below a preconfigured threshold for the class; and communicating the one or more recommendation to a group of recipients specified for the student, wherein the method comprises analyzing geolocation data of the individual data in order to classify a seating position of the student in a classroom, wherein the seating position may be instantiated with a value selected from the group consisting of Front and Back, indicating respective areas within the classroom; and determining the seating position having a Front value as a positive activity and determining the seating position having a Back value as a negative activity, wherein the method comprises comparing the seating position of the student in comparison with a second seating position of a second student in proximity of the student; and discovering that an activity impact score for a peer influence attribute of the second student is less than zero (0), wherein a value of the peer influence attribute is selected from the group consisting of one, zero, negative one (1, 0, −1), wherein one (1) indicates that the second student is helpful to nearby students and attentive, zero (0) indicates that the second student is neutral, and negative one (−1) indicates that the second student is disruptive to the class.

9. The computer program product of claim 8 , the generating comprising: rendering a recommendation not to take a seat near the second student, responsive to determining that the predicted performance is below the preconfigured threshold for the class, wherein the one or more recommendation from the generating includes the recommendation.

10. The computer program product of claim 8 , the generating comprising: rendering a recommendation not to take a seat near the second student.

11. The computer program product of claim 8 , further comprising: analyzing audio data of the real time data for content in order to classify a speech represented by the audio data into respective topics.

12. The computer program product of claim 8 , further comprising: analyzing audio data of the real time data for content in order to classify a speech represented by the audio data into respective topics; and determining the speech having a topic relevant to a subject of the class as a positive activity and determining the speech having a topic irrelevant to the subject as a negative activity.

13. The computer program product of claim 8 , further comprising: analyzing the real time data including audio data and movement data of the student in order to determine whether or not the student participates in the class, wherein participatory activities include raising a hand and asking questions; and discovering that the student does not participate in the class from the analyzing.

14. The computer program product of claim 13 , the generating comprising: rendering a recommendation to participate in the class by performing one or more of the participatory activities, responsive to determining that the predicted performance is below the preconfigured threshold for the class, wherein the one or more recommendation from the generating includes the recommendation.

15. A system comprising: a memory; one or more processor in communication with the memory; and program instructions executable by the one or more processor via the memory to perform a method for providing cognitive education advisory services, comprising: obtaining real time data including individual data from an individual device on person of a student attending a class, by an individual data collection agent running on the individual device, wherein the individual data collection agent communicates with a cognitive education advisor in real time, and wherein the individual device corresponding to the student is registered for the student in a student record for the student; identifying one or more activity of the student during the class from the real time data, based on a configuration for the cognitive education advisor specifying the one or more activities; correlating each of the one or more activity from the identifying with respective impact to performance of the student based on a performance record of the student record for the student, based on the configuration; calculating respective activity impact scores corresponding to the respective impacts, by use of predictive modeling on attributes of each of the one or more activity to the performance of the student; predicting the performance of the student in the class based on a collective activity impact score of the student in the class by adding up the respective activity impact scores from the calculating; generating one or more recommendation in order to improve the performance of the student, responsive to determining that predicted performance from the predicting is below a preconfigured threshold for the class; and communicating the one or more recommendation to a group of recipients specified for the student, wherein the method comprises analyzing geolocation data of the individual data in order to classify a seating position of the student in a classroom, wherein the seating position may be instantiated with a value selected from the group consisting of Front and Back, indicating respective areas within the classroom; and determining the seating position having a Front value as a positive activity and determining the seating position having a Back value as a negative activity, wherein the method comprises comparing the seating position of the student in comparison with a second seating position of a second student in proximity of the student; and discovering that an activity impact score for a peer influence attribute of the second student is less than zero (0), wherein a value of the peer influence attribute is selected from the group consisting of one, zero, negative one (1, 0, −1), wherein one (1) indicates that the second student is helpful to nearby students and attentive, zero (0) indicates that the second student is neutral, and negative one (−1) indicates that the second student is disruptive to the class.

16. The system of claim 15 , the generating comprising: rendering a recommendation not to take a seat near the second student, responsive to determining that the predicted performance is below the preconfigured threshold for the class, wherein the one or more recommendation from the generating includes the recommendation.

17. The system of claim 15 , the generating comprising: rendering a recommendation not to take a seat near the second student.

18. The system of claim 15 , further comprising: analyzing audio data of the real time data for content in order to classify a speech represented by the audio data into respective topics; and determining the speech having a topic relevant to a subject of the class as a positive activity and determining the speech having a topic irrelevant to the subject as a negative activity.

19. The system of claim 15 , further comprising: analyzing the real time data including audio data and movement data of the student in order to determine whether or not the student participates in the class, wherein participatory activities include raising a hand and asking questions; and discovering that the student does not participate in the class from the analyzing.

20. The system of claim 19 , the generating comprising: rendering a recommendation to participate in the class by performing one or more of the participatory activities, responsive to determining that the predicted performance is below the preconfigured threshold for the class, wherein the one or more recommendation from the generating includes the recommendation.